A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing

Andreas Vlachos, Stephen Clark


Abstract
Semantic parsing is the task of translating natural language utterances into a machine-interpretable meaning representation. Most approaches to this task have been evaluated on a small number of existing corpora which assume that all utterances must be interpreted according to a database and typically ignore context. In this paper we present a new, publicly available corpus for context-dependent semantic parsing. The MRL used for the annotation was designed to support a portable, interactive tourist information system. We develop a semantic parser for this corpus by adapting the imitation learning algorithm DAgger without requiring alignment information during training. DAgger improves upon independently trained classifiers by 9.0 and 4.8 points in F-score on the development and test sets respectively.
Anthology ID:
Q14-1042
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
547–560
Language:
URL:
https://aclanthology.org/Q14-1042
DOI:
10.1162/tacl_a_00202
Bibkey:
Cite (ACL):
Andreas Vlachos and Stephen Clark. 2014. A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing. Transactions of the Association for Computational Linguistics, 2:547–560.
Cite (Informal):
A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing (Vlachos & Clark, TACL 2014)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/Q14-1042.pdf